Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    built

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     กระ
    -0.07
     offices
    -0.07
    -leaning
    -0.07
    ペ
    -0.07
     Ви
    -0.07
     Hyde
    -0.07
    दर
    -0.07
    (trigger
    -0.06
     PSU
    -0.06
    　ﾞ
    -0.06
    POSITIVE LOGITS
     damping
    0.06
    building
    0.06
    /';↵
    0.06
     lif
    0.06
    _sections
    0.06
    thur
    0.06
     excessive
    0.06
    \"";↵
    0.06
    (con
    0.06
     hoping
    0.06
    Act Density 0.015%

    No Known Activations